AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Monotone operator equilibrium networks

Ezra Winston, J. Zico Kolter

NeurIPS 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Equilibrium solvers for adversarial games · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a small single-convolution monDEQ instead of Augmented Neural ODECIFAR-10 image classification · CIFAR-10test accuracy: 15.1%Improved
Use a large multi-tier monDEQ with data augmentationCIFAR-10 image classification · CIFAR-10 testtest accuracy: 89%Improved
Use monDEQ rather than Neural ODECIFAR-10 training · CIFAR-10, 40 epochstraining time: 1.4 hours vs 4.4 hoursImproved
Use monDEQ rather than Augmented Neural ODECIFAR-10 training · CIFAR-10, 40 epochsfunction evaluations per minibatch: 20 vs 90Improved
Use Peaceman-Rachford splitting rather than forward-backward splittingmonDEQ equilibrium solving · Fully trained multi-tier CIFAR-10 modelconvergence speedImproved
Use standard DEQ fixed-point solving with Broyden's method instead of the monDEQ solverDEQ with the same multi-tier structure · CIFAR-10 trainingtraining stability: 300 iterationsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy